© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34160
    Prev
    Next
    INDEX
    Explanations

    deduplication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    t
    0.91
    iu
    0.75
     a
    0.73
    ہ
    0.73
    на
    0.70
    p
    0.69
    א
    0.69
    kiego
    0.68
     уй
    0.68
     amiga
    0.67
    POSITIVE LOGITS
    F
    0.91
    V
    0.81
    O
    0.80
    K
    0.79
    有
    0.75
    好
    0.75
    距离
    0.75
    真
    0.73
    是要
    0.73
    N
    0.68
    Activations Density 0.020%

    No Known Activations